mirror of
				https://github.com/go-gitea/gitea.git
				synced 2025-10-29 10:57:44 +09:00 
			
		
		
		
	# ⚠️ Breaking Many deprecated queue config options are removed (actually, they should have been removed in 1.18/1.19). If you see the fatal message when starting Gitea: "Please update your app.ini to remove deprecated config options", please follow the error messages to remove these options from your app.ini. Example: ``` 2023/05/06 19:39:22 [E] Removed queue option: `[indexer].ISSUE_INDEXER_QUEUE_TYPE`. Use new options in `[queue.issue_indexer]` 2023/05/06 19:39:22 [E] Removed queue option: `[indexer].UPDATE_BUFFER_LEN`. Use new options in `[queue.issue_indexer]` 2023/05/06 19:39:22 [F] Please update your app.ini to remove deprecated config options ``` Many options in `[queue]` are are dropped, including: `WRAP_IF_NECESSARY`, `MAX_ATTEMPTS`, `TIMEOUT`, `WORKERS`, `BLOCK_TIMEOUT`, `BOOST_TIMEOUT`, `BOOST_WORKERS`, they can be removed from app.ini. # The problem The old queue package has some legacy problems: * complexity: I doubt few people could tell how it works. * maintainability: Too many channels and mutex/cond are mixed together, too many different structs/interfaces depends each other. * stability: due to the complexity & maintainability, sometimes there are strange bugs and difficult to debug, and some code doesn't have test (indeed some code is difficult to test because a lot of things are mixed together). * general applicability: although it is called "queue", its behavior is not a well-known queue. * scalability: it doesn't seem easy to make it work with a cluster without breaking its behaviors. It came from some very old code to "avoid breaking", however, its technical debt is too heavy now. It's a good time to introduce a better "queue" package. # The new queue package It keeps using old config and concept as much as possible. * It only contains two major kinds of concepts: * The "base queue": channel, levelqueue, redis * They have the same abstraction, the same interface, and they are tested by the same testing code. * The "WokerPoolQueue", it uses the "base queue" to provide "worker pool" function, calls the "handler" to process the data in the base queue. * The new code doesn't do "PushBack" * Think about a queue with many workers, the "PushBack" can't guarantee the order for re-queued unhandled items, so in new code it just does "normal push" * The new code doesn't do "pause/resume" * The "pause/resume" was designed to handle some handler's failure: eg: document indexer (elasticsearch) is down * If a queue is paused for long time, either the producers blocks or the new items are dropped. * The new code doesn't do such "pause/resume" trick, it's not a common queue's behavior and it doesn't help much. * If there are unhandled items, the "push" function just blocks for a few seconds and then re-queue them and retry. * The new code doesn't do "worker booster" * Gitea's queue's handlers are light functions, the cost is only the go-routine, so it doesn't make sense to "boost" them. * The new code only use "max worker number" to limit the concurrent workers. * The new "Push" never blocks forever * Instead of creating more and more blocking goroutines, return an error is more friendly to the server and to the end user. There are more details in code comments: eg: the "Flush" problem, the strange "code.index" hanging problem, the "immediate" queue problem. Almost ready for review. TODO: * [x] add some necessary comments during review * [x] add some more tests if necessary * [x] update documents and config options * [x] test max worker / active worker * [x] re-run the CI tasks to see whether any test is flaky * [x] improve the `handleOldLengthConfiguration` to provide more friendly messages * [x] fine tune default config values (eg: length?) ## Code coverage: 
		
			
				
	
	
		
			111 lines
		
	
	
		
			3.0 KiB
		
	
	
	
		
			Go
		
	
	
	
	
	
			
		
		
	
	
			111 lines
		
	
	
		
			3.0 KiB
		
	
	
	
		
			Go
		
	
	
	
	
	
| // Copyright 2019 The Gitea Authors. All rights reserved.
 | |
| // SPDX-License-Identifier: MIT
 | |
| 
 | |
| package queue
 | |
| 
 | |
| import (
 | |
| 	"context"
 | |
| 	"sync"
 | |
| 	"time"
 | |
| 
 | |
| 	"code.gitea.io/gitea/modules/log"
 | |
| 	"code.gitea.io/gitea/modules/setting"
 | |
| )
 | |
| 
 | |
| // Manager is a manager for the queues created by "CreateXxxQueue" functions, these queues are called "managed queues".
 | |
| type Manager struct {
 | |
| 	mu sync.Mutex
 | |
| 
 | |
| 	qidCounter int64
 | |
| 	Queues     map[int64]ManagedWorkerPoolQueue
 | |
| }
 | |
| 
 | |
| type ManagedWorkerPoolQueue interface {
 | |
| 	GetName() string
 | |
| 	GetType() string
 | |
| 	GetItemTypeName() string
 | |
| 	GetWorkerNumber() int
 | |
| 	GetWorkerActiveNumber() int
 | |
| 	GetWorkerMaxNumber() int
 | |
| 	SetWorkerMaxNumber(num int)
 | |
| 	GetQueueItemNumber() int
 | |
| 
 | |
| 	// FlushWithContext tries to make the handler process all items in the queue synchronously.
 | |
| 	// It is for testing purpose only. It's not designed to be used in a cluster.
 | |
| 	FlushWithContext(ctx context.Context, timeout time.Duration) error
 | |
| }
 | |
| 
 | |
| var manager *Manager
 | |
| 
 | |
| func init() {
 | |
| 	manager = &Manager{
 | |
| 		Queues: make(map[int64]ManagedWorkerPoolQueue),
 | |
| 	}
 | |
| }
 | |
| 
 | |
| func GetManager() *Manager {
 | |
| 	return manager
 | |
| }
 | |
| 
 | |
| func (m *Manager) AddManagedQueue(managed ManagedWorkerPoolQueue) {
 | |
| 	m.mu.Lock()
 | |
| 	defer m.mu.Unlock()
 | |
| 	m.qidCounter++
 | |
| 	m.Queues[m.qidCounter] = managed
 | |
| }
 | |
| 
 | |
| func (m *Manager) GetManagedQueue(qid int64) ManagedWorkerPoolQueue {
 | |
| 	m.mu.Lock()
 | |
| 	defer m.mu.Unlock()
 | |
| 	return m.Queues[qid]
 | |
| }
 | |
| 
 | |
| func (m *Manager) ManagedQueues() map[int64]ManagedWorkerPoolQueue {
 | |
| 	m.mu.Lock()
 | |
| 	defer m.mu.Unlock()
 | |
| 
 | |
| 	queues := make(map[int64]ManagedWorkerPoolQueue, len(m.Queues))
 | |
| 	for k, v := range m.Queues {
 | |
| 		queues[k] = v
 | |
| 	}
 | |
| 	return queues
 | |
| }
 | |
| 
 | |
| // FlushAll tries to make all managed queues process all items synchronously, until timeout or the queue is empty.
 | |
| // It is for testing purpose only. It's not designed to be used in a cluster.
 | |
| func (m *Manager) FlushAll(ctx context.Context, timeout time.Duration) error {
 | |
| 	var finalErr error
 | |
| 	qs := m.ManagedQueues()
 | |
| 	for _, q := range qs {
 | |
| 		if err := q.FlushWithContext(ctx, timeout); err != nil {
 | |
| 			finalErr = err // TODO: in Go 1.20: errors.Join
 | |
| 		}
 | |
| 	}
 | |
| 	return finalErr
 | |
| }
 | |
| 
 | |
| // CreateSimpleQueue creates a simple queue from global setting config provider by name
 | |
| func CreateSimpleQueue[T any](name string, handler HandlerFuncT[T]) *WorkerPoolQueue[T] {
 | |
| 	return createWorkerPoolQueue(name, setting.CfgProvider, handler, false)
 | |
| }
 | |
| 
 | |
| // CreateUniqueQueue creates a unique queue from global setting config provider by name
 | |
| func CreateUniqueQueue[T any](name string, handler HandlerFuncT[T]) *WorkerPoolQueue[T] {
 | |
| 	return createWorkerPoolQueue(name, setting.CfgProvider, handler, true)
 | |
| }
 | |
| 
 | |
| func createWorkerPoolQueue[T any](name string, cfgProvider setting.ConfigProvider, handler HandlerFuncT[T], unique bool) *WorkerPoolQueue[T] {
 | |
| 	queueSetting, err := setting.GetQueueSettings(cfgProvider, name)
 | |
| 	if err != nil {
 | |
| 		log.Error("Failed to get queue settings for %q: %v", name, err)
 | |
| 		return nil
 | |
| 	}
 | |
| 	w, err := NewWorkerPoolQueueBySetting(name, queueSetting, handler, unique)
 | |
| 	if err != nil {
 | |
| 		log.Error("Failed to create queue %q: %v", name, err)
 | |
| 		return nil
 | |
| 	}
 | |
| 	GetManager().AddManagedQueue(w)
 | |
| 	return w
 | |
| }
 |